Portfolio

Purpose of this document

The purpose of this document is to demonstrate some skills I have got in R during my course of “Programming AI with R” in the MBA Artificial Intelligence and Machine Learning given by FIAP University in 2019.

Built with 3.6.2

CLASS 01 (12/06/2019)

Atribuição de Variáveis

x <- 1
y <- 2

Checar o ambiente de programacao

getwd()

## [1] "/Users/arodrigues/Google Drive/FIAP-MBA-8IA/to_git/R"

# setwd("c:/Users/logonpflocal/Documentos/")

Salvar arquivos

# save.image("dados.Rdata")
# save(x, file ="dados.Rdata")
rm(list = ls())

informacao sobre funcoes

?choose.files
help("choose.files")
save.image(choose.files())

## Error in choose.files(): could not find function "choose.files"

instalar pacotes

install.packages("ggplot2")

## Error in contrib.url(repos, "source"): trying to use CRAN without setting a mirror

library("ggplot2")
detach("package:ggplot2", unload = TRUE)

## Error: package 'ggplot2' is required by 'plotly' so will not be detached

remove.packages("ggplot2")

## Removing package from '/Library/Frameworks/R.framework/Versions/3.6/Resources/library'
## (as 'lib' is unspecified)

Arredondamento

x <- 5
y <- pi
y <- round(y, digits = 2)
y

## [1] 3.14

Consultar classe da varia?vel

class(x)

## [1] "numeric"

x <- as.integer(x)

Teste de visualizacao

df <- mtcars
head(df)

##                    mpg cyl disp  hp drat    wt  qsec vs am gear carb
## Mazda RX4         21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
## Mazda RX4 Wag     21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
## Datsun 710        22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
## Hornet 4 Drive    21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
## Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2
## Valiant           18.1   6  225 105 2.76 3.460 20.22  1  0    3    1

ggplot2::qplot(mpg,wt, data=df, colour = as.factor(cyl))

Atribuicao de vetores

vet_num <- c(1,2,3,4)
  #exercicio 2
vetor_a <- c(1,2,3,4)
vetor_b <- c(5,6,7,8)
vetor_c <- vetor_a + vetor_b

Nomeando vetores

idades <- c(34,25,31,17)
names(idades)[1] <- "Wilian"
names(idades) <- c("Wilian","Marcelo","Lucas","Rafael")
idades

##  Wilian Marcelo   Lucas  Rafael 
##      34      25      31      17

idades["Marcelo"]

## Marcelo 
##      25

Matrizes

m1 <- matrix(c(12,22,35,4,5,6,7,8,9), nrow =3)
m1 <- matrix(1:9, nrow = 3)
m1

##      [,1] [,2] [,3]
## [1,]    1    4    7
## [2,]    2    5    8
## [3,]    3    6    9

m1[1:3]

## [1] 1 2 3

Dataframes e seus comandos

df

##                      mpg cyl  disp  hp drat    wt  qsec vs am gear carb
## Mazda RX4           21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
## Mazda RX4 Wag       21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
## Datsun 710          22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1
## Hornet 4 Drive      21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1
## Hornet Sportabout   18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2
## Valiant             18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1
## Duster 360          14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4
## Merc 240D           24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2
## Merc 230            22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2
## Merc 280            19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4
## Merc 280C           17.8   6 167.6 123 3.92 3.440 18.90  1  0    4    4
## Merc 450SE          16.4   8 275.8 180 3.07 4.070 17.40  0  0    3    3
## Merc 450SL          17.3   8 275.8 180 3.07 3.730 17.60  0  0    3    3
## Merc 450SLC         15.2   8 275.8 180 3.07 3.780 18.00  0  0    3    3
## Cadillac Fleetwood  10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4
## Lincoln Continental 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4
## Chrysler Imperial   14.7   8 440.0 230 3.23 5.345 17.42  0  0    3    4
## Fiat 128            32.4   4  78.7  66 4.08 2.200 19.47  1  1    4    1
## Honda Civic         30.4   4  75.7  52 4.93 1.615 18.52  1  1    4    2
## Toyota Corolla      33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1
## Toyota Corona       21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1
## Dodge Challenger    15.5   8 318.0 150 2.76 3.520 16.87  0  0    3    2
## AMC Javelin         15.2   8 304.0 150 3.15 3.435 17.30  0  0    3    2
## Camaro Z28          13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
## Pontiac Firebird    19.2   8 400.0 175 3.08 3.845 17.05  0  0    3    2
## Fiat X1-9           27.3   4  79.0  66 4.08 1.935 18.90  1  1    4    1
## Porsche 914-2       26.0   4 120.3  91 4.43 2.140 16.70  0  1    5    2
## Lotus Europa        30.4   4  95.1 113 3.77 1.513 16.90  1  1    5    2
## Ford Pantera L      15.8   8 351.0 264 4.22 3.170 14.50  0  1    5    4
## Ferrari Dino        19.7   6 145.0 175 3.62 2.770 15.50  0  1    5    6
## Maserati Bora       15.0   8 301.0 335 3.54 3.570 14.60  0  1    5    8
## Volvo 142E          21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2

class(df)

## [1] "data.frame"

head(df, 10)

##                    mpg cyl  disp  hp drat    wt  qsec vs am gear carb
## Mazda RX4         21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
## Mazda RX4 Wag     21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
## Datsun 710        22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1
## Hornet 4 Drive    21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1
## Hornet Sportabout 18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2
## Valiant           18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1
## Duster 360        14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4
## Merc 240D         24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2
## Merc 230          22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2
## Merc 280          19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4

tail(df)

##                 mpg cyl  disp  hp drat    wt qsec vs am gear carb
## Porsche 914-2  26.0   4 120.3  91 4.43 2.140 16.7  0  1    5    2
## Lotus Europa   30.4   4  95.1 113 3.77 1.513 16.9  1  1    5    2
## Ford Pantera L 15.8   8 351.0 264 4.22 3.170 14.5  0  1    5    4
## Ferrari Dino   19.7   6 145.0 175 3.62 2.770 15.5  0  1    5    6
## Maserati Bora  15.0   8 301.0 335 3.54 3.570 14.6  0  1    5    8
## Volvo 142E     21.4   4 121.0 109 4.11 2.780 18.6  1  1    4    2

ncol(df)

## [1] 11

nrow(df)

## [1] 32

summary(df)

##       mpg             cyl             disp             hp       
##  Min.   :10.40   Min.   :4.000   Min.   : 71.1   Min.   : 52.0  
##  1st Qu.:15.43   1st Qu.:4.000   1st Qu.:120.8   1st Qu.: 96.5  
##  Median :19.20   Median :6.000   Median :196.3   Median :123.0  
##  Mean   :20.09   Mean   :6.188   Mean   :230.7   Mean   :146.7  
##  3rd Qu.:22.80   3rd Qu.:8.000   3rd Qu.:326.0   3rd Qu.:180.0  
##  Max.   :33.90   Max.   :8.000   Max.   :472.0   Max.   :335.0  
##       drat             wt             qsec             vs        
##  Min.   :2.760   Min.   :1.513   Min.   :14.50   Min.   :0.0000  
##  1st Qu.:3.080   1st Qu.:2.581   1st Qu.:16.89   1st Qu.:0.0000  
##  Median :3.695   Median :3.325   Median :17.71   Median :0.0000  
##  Mean   :3.597   Mean   :3.217   Mean   :17.85   Mean   :0.4375  
##  3rd Qu.:3.920   3rd Qu.:3.610   3rd Qu.:18.90   3rd Qu.:1.0000  
##  Max.   :4.930   Max.   :5.424   Max.   :22.90   Max.   :1.0000  
##        am              gear            carb      
##  Min.   :0.0000   Min.   :3.000   Min.   :1.000  
##  1st Qu.:0.0000   1st Qu.:3.000   1st Qu.:2.000  
##  Median :0.0000   Median :4.000   Median :2.000  
##  Mean   :0.4062   Mean   :3.688   Mean   :2.812  
##  3rd Qu.:1.0000   3rd Qu.:4.000   3rd Qu.:4.000  
##  Max.   :1.0000   Max.   :5.000   Max.   :8.000

c <- diamonds

## Error in eval(expr, envir, enclos): cannot open file '/Library/Frameworks/R.framework/Versions/3.6/Resources/library/ggplot2/data/Rdata.rdb': No such file or directory

library("ggplot2")
head(diamonds)

## Warning in head(diamonds): restarting interrupted promise evaluation

## Error in head(diamonds): cannot open file '/Library/Frameworks/R.framework/Versions/3.6/Resources/library/ggplot2/data/Rdata.rdb': No such file or directory

ggplot2::qplot(carat,price, data=c)

## Error: You're passing a function as global data.
## Have you misspelled the `data` argument in `ggplot()`

class(diamonds)

## Warning: restarting interrupted promise evaluation

## Error in eval(expr, envir, enclos): cannot open file '/Library/Frameworks/R.framework/Versions/3.6/Resources/library/ggplot2/data/Rdata.rdb': No such file or directory

lapply(mtcars, class)

## $mpg
## [1] "numeric"
## 
## $cyl
## [1] "numeric"
## 
## $disp
## [1] "numeric"
## 
## $hp
## [1] "numeric"
## 
## $drat
## [1] "numeric"
## 
## $wt
## [1] "numeric"
## 
## $qsec
## [1] "numeric"
## 
## $vs
## [1] "numeric"
## 
## $am
## [1] "numeric"
## 
## $gear
## [1] "numeric"
## 
## $carb
## [1] "numeric"

Exercicio final

m1 <- matrix(seq(2L,32L,2L), nrow = 4, ncol = 4)
m1

##      [,1] [,2] [,3] [,4]
## [1,]    2   10   18   26
## [2,]    4   12   20   28
## [3,]    6   14   22   30
## [4,]    8   16   24   32

m2 <- matrix((1:16), nrow = 4) *2
m2

##      [,1] [,2] [,3] [,4]
## [1,]    2   10   18   26
## [2,]    4   12   20   28
## [3,]    6   14   22   30
## [4,]    8   16   24   32

Exercicio final dataframe

df1 <- data.frame(row.names = c("L1","L2","L3","L4")
                  , nome_vetor_1 = v1
                  , nome_vetor_2 = v2
                  , nome_vetor_3 = v3
                  , nome_vetor_4 = v4
                  , nome_vetor_5 = v5)

## Error in data.frame(row.names = c("L1", "L2", "L3", "L4"), nome_vetor_1 = v1, : object 'v1' not found

CLASS 02 - (27/06/2019)

Instalacao mais fácil do R markdown

# path <- "http://raw.githubusercontent.com/elthonf/fiap-mba-r/master/"
# source(file = paste0(path, 'gereral_codes/inst_rmarkdown.r'))

Sequencias

vetor_1 <- 1:9
vetor_2 <- 80:32
vetor_3 <- 4:-2
vetor_4 <- 3:3
vetor_5 <- seq(1,9)
identical(vetor_1, vetor_5)

## [1] TRUE

vetor_6 <- seq(1,10, by = 2)
vetor_7 <- seq(1,10, by = pi)
seq(15)

##  [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15

seq(0,1, length.out = 12)

##  [1] 0.00000000 0.09090909 0.18181818 0.27272727 0.36363636 0.45454545
##  [7] 0.54545455 0.63636364 0.72727273 0.81818182 0.90909091 1.00000000

seq(8,10, along.with = c(1,1))

## [1]  8 10

seq_along(c(1,56,21))

## [1] 1 2 3

seq_len(5)

## [1] 1 2 3 4 5

Repeticao

rep(0, times = 5)

## [1] 0 0 0 0 0

rep(c(1,2,3), times = 3)

## [1] 1 2 3 1 2 3 1 2 3

rep(c(1,2,3), each = 3)

## [1] 1 1 1 2 2 2 3 3 3

rep(12, length.out = 4)

## [1] 12 12 12 12

rep(c(1,2,3), length.out = 7)

## [1] 1 2 3 1 2 3 1

my_seq <- seq(5,10, length.out = 30)
length(my_seq)

## [1] 30

10:pi

## [1] 10  9  8  7  6  5  4

pi:10

## [1] 3.141593 4.141593 5.141593 6.141593 7.141593 8.141593 9.141593

seq_along(my_seq)

##  [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25
## [26] 26 27 28 29 30

seq(along.with = my_seq)

##  [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25
## [26] 26 27 28 29 30

seq(1,length(my_seq), along.with = my_seq)

##  [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25
## [26] 26 27 28 29 30

c(1,2,3,NA)

## [1]  1  2  3 NA

c(1,2,3,NULL)

## [1] 1 2 3

vet1 <- c(1L,3L, NA)
class(vet1)

## [1] "integer"

mean(vet1)

## [1] NA

Example dataframe

Name <- c("joão","maria","diego")
Sex <- c("male",NA,"male")
Age <- c(45,NA, NA)
dt <- data.frame(Name, Sex, Age)
dt

##    Name  Sex Age
## 1  joão male  45
## 2 maria <NA>  NA
## 3 diego male  NA

is.na(dt)

##       Name   Sex   Age
## [1,] FALSE FALSE FALSE
## [2,] FALSE  TRUE  TRUE
## [3,] FALSE FALSE  TRUE

sum(is.na(dt))

## [1] 3

c <- 19/0
is.infinite(c)

## [1] TRUE

Subconjunto
- Vetor

vetor_1

## [1] 1 2 3 4 5 6 7 8 9

vetor_1[2:5]

## [1] 2 3 4 5

Dataframe

mtcars

##                      mpg cyl  disp  hp drat    wt  qsec vs am gear carb
## Mazda RX4           21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
## Mazda RX4 Wag       21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
## Datsun 710          22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1
## Hornet 4 Drive      21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1
## Hornet Sportabout   18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2
## Valiant             18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1
## Duster 360          14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4
## Merc 240D           24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2
## Merc 230            22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2
## Merc 280            19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4
## Merc 280C           17.8   6 167.6 123 3.92 3.440 18.90  1  0    4    4
## Merc 450SE          16.4   8 275.8 180 3.07 4.070 17.40  0  0    3    3
## Merc 450SL          17.3   8 275.8 180 3.07 3.730 17.60  0  0    3    3
## Merc 450SLC         15.2   8 275.8 180 3.07 3.780 18.00  0  0    3    3
## Cadillac Fleetwood  10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4
## Lincoln Continental 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4
## Chrysler Imperial   14.7   8 440.0 230 3.23 5.345 17.42  0  0    3    4
## Fiat 128            32.4   4  78.7  66 4.08 2.200 19.47  1  1    4    1
## Honda Civic         30.4   4  75.7  52 4.93 1.615 18.52  1  1    4    2
## Toyota Corolla      33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1
## Toyota Corona       21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1
## Dodge Challenger    15.5   8 318.0 150 2.76 3.520 16.87  0  0    3    2
## AMC Javelin         15.2   8 304.0 150 3.15 3.435 17.30  0  0    3    2
## Camaro Z28          13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
## Pontiac Firebird    19.2   8 400.0 175 3.08 3.845 17.05  0  0    3    2
## Fiat X1-9           27.3   4  79.0  66 4.08 1.935 18.90  1  1    4    1
## Porsche 914-2       26.0   4 120.3  91 4.43 2.140 16.70  0  1    5    2
## Lotus Europa        30.4   4  95.1 113 3.77 1.513 16.90  1  1    5    2
## Ford Pantera L      15.8   8 351.0 264 4.22 3.170 14.50  0  1    5    4
## Ferrari Dino        19.7   6 145.0 175 3.62 2.770 15.50  0  1    5    6
## Maserati Bora       15.0   8 301.0 335 3.54 3.570 14.60  0  1    5    8
## Volvo 142E          21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2

mtcars[1,2]

## [1] 6

mtcars[1:5,2]

## [1] 6 6 4 6 8

mtcars[1:5, 1:5]

##                    mpg cyl disp  hp drat
## Mazda RX4         21.0   6  160 110 3.90
## Mazda RX4 Wag     21.0   6  160 110 3.90
## Datsun 710        22.8   4  108  93 3.85
## Hornet 4 Drive    21.4   6  258 110 3.08
## Hornet Sportabout 18.7   8  360 175 3.15

mtcars[1:5, c(1,2,4)]

##                    mpg cyl  hp
## Mazda RX4         21.0   6 110
## Mazda RX4 Wag     21.0   6 110
## Datsun 710        22.8   4  93
## Hornet 4 Drive    21.4   6 110
## Hornet Sportabout 18.7   8 175

mtcars["Mazda RX4",c("mpg","cyl","hp")] #like

##           mpg cyl  hp
## Mazda RX4  21   6 110

lista <- list(a = c(1,2,3), b= c("casa","comida","roupalavada"), c = c(Inf, NA, -Inf))
lista["a"]

## $a
## [1] 1 2 3

class(lista["a"])

## [1] "list"

lista[["a"]]

## [1] 1 2 3

lista$a

## [1] 1 2 3

install.packages("sqldf")

## Error in contrib.url(repos, "source"): trying to use CRAN without setting a mirror

library(sqldf)

## Error in library(sqldf): there is no package called 'sqldf'

sqldf("select cyl,hp from mtcars")

## Error in sqldf("select cyl,hp from mtcars"): could not find function "sqldf"

Data

dia_texto <- "19/02/1990 T 07:45:30"
dia_date <- as.Date(dia_texto, "%d/%m/%Y T %H:%M:%S", tz= "America/Sao_Paulo")
dia.time1 <- as.POSIXct(dia_texto, format = "%d/%m/%Y T %H:%M:%S", tz= "America/Sao_Paulo")
dia.time1

## [1] "1990-02-19 07:45:30 -03"

Mostra o que está acontecendo por trás

unclass(dia.time1)

## [1] 635424330
## attr(,"tzone")
## [1] "America/Sao_Paulo"

dia.time2 <- as.POSIXlt(dia_texto, format = "%d/%m/%Y T %H:%M:%S", tz= "America/Sao_Paulo")
unclass(dia.time2)

## $sec
## [1] 30
## 
## $min
## [1] 45
## 
## $hour
## [1] 7
## 
## $mday
## [1] 19
## 
## $mon
## [1] 1
## 
## $year
## [1] 90
## 
## $wday
## [1] 1
## 
## $yday
## [1] 49
## 
## $isdst
## [1] 0
## 
## $zone
## [1] "-03"
## 
## $gmtoff
## [1] NA
## 
## attr(,"tzone")
## [1] "America/Sao_Paulo"

dia.time2$mon

## [1] 1

Biblioteca para a gestão de dados de data e tempo

install.packages("lubridate")

## Error in contrib.url(repos, "source"): trying to use CRAN without setting a mirror

library(lubridate)

## Error in library(lubridate): there is no package called 'lubridate'

lub_date1 <- ymd("20110604")

## Error in ymd("20110604"): could not find function "ymd"

lub_date1

## Error in eval(expr, envir, enclos): object 'lub_date1' not found

date_1 <- as.Date("2011-06-04")
date_1

## [1] "2011-06-04"

identical(lub_date1, date_1)

## Error in identical(lub_date1, date_1): object 'lub_date1' not found

lub_date2 <- dmy("01-02-1988")

## Error in dmy("01-02-1988"): could not find function "dmy"

lub_date2

## Error in eval(expr, envir, enclos): object 'lub_date2' not found

System

now()

## Error in now(): could not find function "now"

today()

## Error in today(): could not find function "today"

Operacoes com data

lub_date3 <- lub_date2 + ddays(2) + dyears(1)

## Error in eval(expr, envir, enclos): object 'lub_date2' not found

lub_date2

## Error in eval(expr, envir, enclos): object 'lub_date2' not found

lub_date3

## Error in eval(expr, envir, enclos): object 'lub_date3' not found

Resolucao do exercicio

lub1 <- as.duration(260)

## Error in as.duration(260): could not find function "as.duration"

lub2 <- duration(num = 260, units = "minutes")/60

## Error in duration(num = 260, units = "minutes"): could not find function "duration"

lub2

## Error in eval(expr, envir, enclos): object 'lub2' not found

lub3 <- duration(num = 1, units = "days") - duration(num=60, units = "minutes")

## Error in duration(num = 1, units = "days"): could not find function "duration"

lub3

## Error in eval(expr, envir, enclos): object 'lub3' not found

lub4 <- c(ddays(x=12), dhours(x=5),dminutes(x=10))

## Error in ddays(x = 12): could not find function "ddays"

lub4

## Error in eval(expr, envir, enclos): object 'lub4' not found

Exercicio BF

  #definindo o primeiro dia de janeiro
dtentrada = dmy("01-11-2019")

## Error in dmy("01-11-2019"): could not find function "dmy"

dtentrada

## Error in eval(expr, envir, enclos): object 'dtentrada' not found

  #qual dia da semana cai o primeiro dia
wday(dtentrada)

## Error in wday(dtentrada): could not find function "wday"

  #criando criterios para avaliar o que fazer ao descobrir o dia da semana
    # Opcoes (coordenadas pelos dois ifelse`s`)
      #Se igual a 5 (quinta-feira), a variavel bf_check recebe 0 - como ? quinta n?o preciso mudar
      #Se maior que 5 - 6 ou 7 - a variavel recebe 12 menos o wday(dtentrada) (6 ou 7) - como ? maior que 5 adiciono o que falta para a pr?xima quinta-feira 
      #Se menor que 5 - 1,2,3,4 - a variavel recebe 5 menos o wday(dtentrada) (1,2,3 ou 4) como ? menor que 5, adiciono o que falta para ser 5
bf_check <- ifelse(wday(dtentrada) == 5, 0, 
                   ifelse(wday(dtentrada)>5, 12-wday(dtentrada), 5-wday(dtentrada)))

## Error in wday(dtentrada): could not find function "wday"

bf_check

## Error in eval(expr, envir, enclos): object 'bf_check' not found

Adiconando 3 componentes ao primeiro dia de novembro

    # 3 semanas para chegar na quarta semana de novembro (dweeks(3))
    # 1 dia para sair da quinta-feira e ir para sexta-feira da BF (ddays(1))
    # correcao para o dia da semana como explicado acima (ddays(bf_check))
bf <- dtentrada + dweeks(3) + ddays(1) + ddays(bf_check)

## Error in eval(expr, envir, enclos): object 'dtentrada' not found

bf

## Error in eval(expr, envir, enclos): object 'bf' not found

CLASS 03 (17/08/2019)

Vetores:

a <- c(334911, 19760626, 759, 096181, 7843)
a

## [1]   334911 19760626      759    96181     7843

b <- 2 * a
b

## [1]   669822 39521252     1518   192362    15686

c <- b / 3
c

## [1]   223274.000 13173750.667      506.000    64120.667     5228.667

d <- c + a ** 2
d

## [1] 1.121656e+11 3.904824e+14 5.765870e+05 9.250849e+09 6.151788e+07

d <- c + a ^ 2
d

## [1] 1.121656e+11 3.904824e+14 5.765870e+05 9.250849e+09 6.151788e+07

d <- a * a
d

## [1] 1.121654e+11 3.904823e+14 5.760810e+05 9.250785e+09 6.151265e+07

e <- sqrt(d)
e

## [1]   334911 19760626      759    96181     7843

e <- d ^ 1/2
e

## [1] 5.608269e+10 1.952412e+14 2.880405e+05 4.625392e+09 3.075632e+07

ai <- rev(a)
ai

## [1]     7843    96181      759 19760626   334911

ai <- a[5:1]
ai

## [1]     7843    96181      759 19760626   334911

Como acessar o help:

?sum()

## Warning in read.dcf(file.path(p, "DESCRIPTION"), c("Package", "Version")):
## cannot open compressed file '/Library/Frameworks/R.framework/Versions/3.6/
## Resources/library/ggplot2/DESCRIPTION', probable reason 'No such file or
## directory'

## Warning in find.package(if (is.null(package)) loadedNamespaces() else package, :
## there is no package called 'ggplot2'

Mostrar todas as fun??es do Pacote Base no pop up:

base::

## Error: <text>:2:0: unexpected end of line
## 1: base::
##    ^

Matrizes:
- Usando matriz, todos os dados devem ser do mesmo tipo.
- No dataframe é possível misturar os tipos de dados.

M <- matrix(1:8, ncol = 2)
M

##      [,1] [,2]
## [1,]    1    5
## [2,]    2    6
## [3,]    3    7
## [4,]    4    8

M0 <- matrix(1:8, ncol = 2, byrow = TRUE)
M0

##      [,1] [,2]
## [1,]    1    2
## [2,]    3    4
## [3,]    5    6
## [4,]    7    8

M1 <- matrix(c(a, b, c, d, e, ai), ncol = 5, byrow = TRUE)
M1

##              [,1]         [,2]     [,3]         [,4]         [,5]
## [1,]       334911 1.976063e+07    759.0 9.618100e+04     7843.000
## [2,]       669822 3.952125e+07   1518.0 1.923620e+05    15686.000
## [3,]       223274 1.317375e+07    506.0 6.412067e+04     5228.667
## [4,] 112165377921 3.904823e+14 576081.0 9.250785e+09 61512649.000
## [5,]  56082688960 1.952412e+14 288040.5 4.625392e+09 30756324.500
## [6,]         7843 9.618100e+04    759.0 1.976063e+07   334911.000

M2 <- matrix(c(a, b, c, d, e, ai), ncol = 6, byrow = FALSE)

Por default, o byrow é False. Para melhor desempenho, o ideal é omitir esse argumento.

M2

##          [,1]     [,2]         [,3]         [,4]         [,5]     [,6]
## [1,]   334911   669822   223274.000 1.121654e+11 5.608269e+10     7843
## [2,] 19760626 39521252 13173750.667 3.904823e+14 1.952412e+14    96181
## [3,]      759     1518      506.000 5.760810e+05 2.880405e+05      759
## [4,]    96181   192362    64120.667 9.250785e+09 4.625392e+09 19760626
## [5,]     7843    15686     5228.667 6.151265e+07 3.075632e+07   334911

M3 <- 0.1 * M1
M3

##              [,1]         [,2]     [,3]         [,4]         [,5]
## [1,] 3.349110e+04 1.976063e+06    75.90 9.618100e+03     784.3000
## [2,] 6.698220e+04 3.952125e+06   151.80 1.923620e+04    1568.6000
## [3,] 2.232740e+04 1.317375e+06    50.60 6.412067e+03     522.8667
## [4,] 1.121654e+10 3.904823e+13 57608.10 9.250785e+08 6151264.9000
## [5,] 5.608269e+09 1.952412e+13 28804.05 4.625392e+08 3075632.4500
## [6,] 7.843000e+02 9.618100e+03    75.90 1.976063e+06   33491.1000

M <- as.matrix(attitude)
M4 <- M[10:14, 1:6]
M4

##      rating complaints privileges learning raises critical
## [1,]     67         61         45       47     62       80
## [2,]     64         53         53       58     58       67
## [3,]     67         60         47       39     59       74
## [4,]     69         62         57       42     55       63
## [5,]     68         83         83       45     59       77

Save Images

# save.image("C:/Users/logonrmlocal/Downloads/var.RData")

Mostra os dados em outro tab

# View(attitude)

Mostra oa classe do objeto:

class(attitude)

## [1] "data.frame"

Mostra a dimensão do objeto. Linhas, Colunas

dim(attitude)

## [1] 30  7

Converte o dataframe em matriz

attitude

##    rating complaints privileges learning raises critical advance
## 1      43         51         30       39     61       92      45
## 2      63         64         51       54     63       73      47
## 3      71         70         68       69     76       86      48
## 4      61         63         45       47     54       84      35
## 5      81         78         56       66     71       83      47
## 6      43         55         49       44     54       49      34
## 7      58         67         42       56     66       68      35
## 8      71         75         50       55     70       66      41
## 9      72         82         72       67     71       83      31
## 10     67         61         45       47     62       80      41
## 11     64         53         53       58     58       67      34
## 12     67         60         47       39     59       74      41
## 13     69         62         57       42     55       63      25
## 14     68         83         83       45     59       77      35
## 15     77         77         54       72     79       77      46
## 16     81         90         50       72     60       54      36
## 17     74         85         64       69     79       79      63
## 18     65         60         65       75     55       80      60
## 19     65         70         46       57     75       85      46
## 20     50         58         68       54     64       78      52
## 21     50         40         33       34     43       64      33
## 22     64         61         52       62     66       80      41
## 23     53         66         52       50     63       80      37
## 24     40         37         42       58     50       57      49
## 25     63         54         42       48     66       75      33
## 26     66         77         66       63     88       76      72
## 27     78         75         58       74     80       78      49
## 28     48         57         44       45     51       83      38
## 29     85         85         71       71     77       74      55
## 30     82         82         39       59     64       78      39

as.matrix(attitude)

##       rating complaints privileges learning raises critical advance
##  [1,]     43         51         30       39     61       92      45
##  [2,]     63         64         51       54     63       73      47
##  [3,]     71         70         68       69     76       86      48
##  [4,]     61         63         45       47     54       84      35
##  [5,]     81         78         56       66     71       83      47
##  [6,]     43         55         49       44     54       49      34
##  [7,]     58         67         42       56     66       68      35
##  [8,]     71         75         50       55     70       66      41
##  [9,]     72         82         72       67     71       83      31
## [10,]     67         61         45       47     62       80      41
## [11,]     64         53         53       58     58       67      34
## [12,]     67         60         47       39     59       74      41
## [13,]     69         62         57       42     55       63      25
## [14,]     68         83         83       45     59       77      35
## [15,]     77         77         54       72     79       77      46
## [16,]     81         90         50       72     60       54      36
## [17,]     74         85         64       69     79       79      63
## [18,]     65         60         65       75     55       80      60
## [19,]     65         70         46       57     75       85      46
## [20,]     50         58         68       54     64       78      52
## [21,]     50         40         33       34     43       64      33
## [22,]     64         61         52       62     66       80      41
## [23,]     53         66         52       50     63       80      37
## [24,]     40         37         42       58     50       57      49
## [25,]     63         54         42       48     66       75      33
## [26,]     66         77         66       63     88       76      72
## [27,]     78         75         58       74     80       78      49
## [28,]     48         57         44       45     51       83      38
## [29,]     85         85         71       71     77       74      55
## [30,]     82         82         39       59     64       78      39

Transforma os dados de string para categorias com uma ordem (levels):

sexo <- rep(c("F", "M"), 5)
sexo

##  [1] "F" "M" "F" "M" "F" "M" "F" "M" "F" "M"

factor(sexo) #

##  [1] F M F M F M F M F M
## Levels: F M

Exercicio

M19 <- matrix(c(1,2), ncol = 19, nrow = 19)

## Warning in matrix(c(1, 2), ncol = 19, nrow = 19): data length [2] is not a sub-
## multiple or multiple of the number of rows [19]

M19

##       [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10] [,11] [,12] [,13]
##  [1,]    1    2    1    2    1    2    1    2    1     2     1     2     1
##  [2,]    2    1    2    1    2    1    2    1    2     1     2     1     2
##  [3,]    1    2    1    2    1    2    1    2    1     2     1     2     1
##  [4,]    2    1    2    1    2    1    2    1    2     1     2     1     2
##  [5,]    1    2    1    2    1    2    1    2    1     2     1     2     1
##  [6,]    2    1    2    1    2    1    2    1    2     1     2     1     2
##  [7,]    1    2    1    2    1    2    1    2    1     2     1     2     1
##  [8,]    2    1    2    1    2    1    2    1    2     1     2     1     2
##  [9,]    1    2    1    2    1    2    1    2    1     2     1     2     1
## [10,]    2    1    2    1    2    1    2    1    2     1     2     1     2
## [11,]    1    2    1    2    1    2    1    2    1     2     1     2     1
## [12,]    2    1    2    1    2    1    2    1    2     1     2     1     2
## [13,]    1    2    1    2    1    2    1    2    1     2     1     2     1
## [14,]    2    1    2    1    2    1    2    1    2     1     2     1     2
## [15,]    1    2    1    2    1    2    1    2    1     2     1     2     1
## [16,]    2    1    2    1    2    1    2    1    2     1     2     1     2
## [17,]    1    2    1    2    1    2    1    2    1     2     1     2     1
## [18,]    2    1    2    1    2    1    2    1    2     1     2     1     2
## [19,]    1    2    1    2    1    2    1    2    1     2     1     2     1
##       [,14] [,15] [,16] [,17] [,18] [,19]
##  [1,]     2     1     2     1     2     1
##  [2,]     1     2     1     2     1     2
##  [3,]     2     1     2     1     2     1
##  [4,]     1     2     1     2     1     2
##  [5,]     2     1     2     1     2     1
##  [6,]     1     2     1     2     1     2
##  [7,]     2     1     2     1     2     1
##  [8,]     1     2     1     2     1     2
##  [9,]     2     1     2     1     2     1
## [10,]     1     2     1     2     1     2
## [11,]     2     1     2     1     2     1
## [12,]     1     2     1     2     1     2
## [13,]     2     1     2     1     2     1
## [14,]     1     2     1     2     1     2
## [15,]     2     1     2     1     2     1
## [16,]     1     2     1     2     1     2
## [17,]     2     1     2     1     2     1
## [18,]     1     2     1     2     1     2
## [19,]     2     1     2     1     2     1

M191 <- m19 -1

## Error in eval(expr, envir, enclos): object 'm19' not found

M191

## Error in eval(expr, envir, enclos): object 'M191' not found

M1919 <- m191 + 1:19

## Error in eval(expr, envir, enclos): object 'm191' not found

M1919

## Error in eval(expr, envir, enclos): object 'M1919' not found

Exercicio Multiplicacao de Matrizes

M5 <- M1 * M3
M5

##              [,1]         [,2]         [,3]         [,4]         [,5]
## [1,] 1.121654e+10 3.904823e+13 5.760810e+04 9.250785e+08 6.151265e+06
## [2,] 4.486615e+10 1.561929e+14 2.304324e+05 3.700314e+09 2.460506e+07
## [3,] 4.985128e+09 1.735477e+13 2.560360e+04 4.111460e+08 2.733896e+06
## [4,] 1.258107e+21 1.524765e+28 3.318693e+10 8.557702e+18 3.783806e+14
## [5,] 3.145268e+20 3.811911e+27 8.296733e+09 2.139425e+18 9.459515e+13
## [6,] 6.151265e+06 9.250785e+08 5.760810e+04 3.904823e+13 1.121654e+10

M6 <- M3 * M1
M6

##              [,1]         [,2]         [,3]         [,4]         [,5]
## [1,] 1.121654e+10 3.904823e+13 5.760810e+04 9.250785e+08 6.151265e+06
## [2,] 4.486615e+10 1.561929e+14 2.304324e+05 3.700314e+09 2.460506e+07
## [3,] 4.985128e+09 1.735477e+13 2.560360e+04 4.111460e+08 2.733896e+06
## [4,] 1.258107e+21 1.524765e+28 3.318693e+10 8.557702e+18 3.783806e+14
## [5,] 3.145268e+20 3.811911e+27 8.296733e+09 2.139425e+18 9.459515e+13
## [6,] 6.151265e+06 9.250785e+08 5.760810e+04 3.904823e+13 1.121654e+10

M7 <- M1 %*% M4
M7

##            rating   complaints   privileges     learning       raises
## [1,] 1.294340e+09 1.074402e+09 1.068553e+09 1.166279e+09 1.172678e+09
## [2,] 2.588680e+09 2.148805e+09 2.137106e+09 2.332559e+09 2.345357e+09
## [3,] 8.628932e+08 7.162683e+08 7.123688e+08 7.775195e+08 7.817855e+08
## [4,] 2.499903e+16 2.070298e+16 2.070114e+16 2.265364e+16 2.265544e+16
## [5,] 1.249951e+16 1.035149e+16 1.035057e+16 1.132682e+16 1.132772e+16
## [6,] 1.392989e+09 1.258578e+09 1.159639e+09 8.509940e+08 1.112704e+09
##          critical
## [1,] 1.357474e+09
## [2,] 2.714949e+09
## [3,] 9.049829e+08
## [4,] 2.617188e+16
## [5,] 1.308594e+16
## [6,] 1.277835e+09

M8 <- M4 %*% M1
M8

##              [,1]         [,2]     [,3]         [,4]       [,5]
## [1,] 8.748973e+12 3.045763e+16 45161259 723163125077 4826497119
## [2,] 9.758457e+12 3.397197e+16 50325748 806161985314 5375649929
## [3,] 7.683402e+12 2.674804e+16 39683430 635162041971 4240112259
## [4,] 7.795572e+12 2.713853e+16 40260776 644196678138 4298040232
## [5,] 8.356418e+12 2.909094e+16 43196082 690732861266 4610749739

M5 == M6

##      [,1] [,2] [,3] [,4] [,5]
## [1,] TRUE TRUE TRUE TRUE TRUE
## [2,] TRUE TRUE TRUE TRUE TRUE
## [3,] TRUE TRUE TRUE TRUE TRUE
## [4,] TRUE TRUE TRUE TRUE TRUE
## [5,] TRUE TRUE TRUE TRUE TRUE
## [6,] TRUE TRUE TRUE TRUE TRUE

M7 == M8

## Error in M7 == M8: non-conformable arrays

Matrix Transposta

M <- as.matrix(attitude)
M

##       rating complaints privileges learning raises critical advance
##  [1,]     43         51         30       39     61       92      45
##  [2,]     63         64         51       54     63       73      47
##  [3,]     71         70         68       69     76       86      48
##  [4,]     61         63         45       47     54       84      35
##  [5,]     81         78         56       66     71       83      47
##  [6,]     43         55         49       44     54       49      34
##  [7,]     58         67         42       56     66       68      35
##  [8,]     71         75         50       55     70       66      41
##  [9,]     72         82         72       67     71       83      31
## [10,]     67         61         45       47     62       80      41
## [11,]     64         53         53       58     58       67      34
## [12,]     67         60         47       39     59       74      41
## [13,]     69         62         57       42     55       63      25
## [14,]     68         83         83       45     59       77      35
## [15,]     77         77         54       72     79       77      46
## [16,]     81         90         50       72     60       54      36
## [17,]     74         85         64       69     79       79      63
## [18,]     65         60         65       75     55       80      60
## [19,]     65         70         46       57     75       85      46
## [20,]     50         58         68       54     64       78      52
## [21,]     50         40         33       34     43       64      33
## [22,]     64         61         52       62     66       80      41
## [23,]     53         66         52       50     63       80      37
## [24,]     40         37         42       58     50       57      49
## [25,]     63         54         42       48     66       75      33
## [26,]     66         77         66       63     88       76      72
## [27,]     78         75         58       74     80       78      49
## [28,]     48         57         44       45     51       83      38
## [29,]     85         85         71       71     77       74      55
## [30,]     82         82         39       59     64       78      39

MT <- t(M)
MT

##            [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10] [,11] [,12] [,13]
## rating       43   63   71   61   81   43   58   71   72    67    64    67    69
## complaints   51   64   70   63   78   55   67   75   82    61    53    60    62
## privileges   30   51   68   45   56   49   42   50   72    45    53    47    57
## learning     39   54   69   47   66   44   56   55   67    47    58    39    42
## raises       61   63   76   54   71   54   66   70   71    62    58    59    55
## critical     92   73   86   84   83   49   68   66   83    80    67    74    63
## advance      45   47   48   35   47   34   35   41   31    41    34    41    25
##            [,14] [,15] [,16] [,17] [,18] [,19] [,20] [,21] [,22] [,23] [,24]
## rating        68    77    81    74    65    65    50    50    64    53    40
## complaints    83    77    90    85    60    70    58    40    61    66    37
## privileges    83    54    50    64    65    46    68    33    52    52    42
## learning      45    72    72    69    75    57    54    34    62    50    58
## raises        59    79    60    79    55    75    64    43    66    63    50
## critical      77    77    54    79    80    85    78    64    80    80    57
## advance       35    46    36    63    60    46    52    33    41    37    49
##            [,25] [,26] [,27] [,28] [,29] [,30]
## rating        63    66    78    48    85    82
## complaints    54    77    75    57    85    82
## privileges    42    66    58    44    71    39
## learning      48    63    74    45    71    59
## raises        66    88    80    51    77    64
## critical      75    76    78    83    74    78
## advance       33    72    49    38    55    39

diag

vet <- 1:9
diag(vet)

##       [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9]
##  [1,]    1    0    0    0    0    0    0    0    0
##  [2,]    0    2    0    0    0    0    0    0    0
##  [3,]    0    0    3    0    0    0    0    0    0
##  [4,]    0    0    0    4    0    0    0    0    0
##  [5,]    0    0    0    0    5    0    0    0    0
##  [6,]    0    0    0    0    0    6    0    0    0
##  [7,]    0    0    0    0    0    0    7    0    0
##  [8,]    0    0    0    0    0    0    0    8    0
##  [9,]    0    0    0    0    0    0    0    0    9

diag(5, nrow = 10, ncol = 5)

##       [,1] [,2] [,3] [,4] [,5]
##  [1,]    5    0    0    0    0
##  [2,]    0    5    0    0    0
##  [3,]    0    0    5    0    0
##  [4,]    0    0    0    5    0
##  [5,]    0    0    0    0    5
##  [6,]    0    0    0    0    0
##  [7,]    0    0    0    0    0
##  [8,]    0    0    0    0    0
##  [9,]    0    0    0    0    0
## [10,]    0    0    0    0    0

# Matriz Identidade:

M %*% I = M

## Error in M %*% I = M: could not find function "%*%<-"

Solve usado para calcular a Matriz Inversa (M?)
- Matriz Inversa: $M %*% M? = I --> O (n^2 + log(n))$ == High CPU intensive

A <- as.matrix(attitude[21:25, 1:5])
A

##    rating complaints privileges learning raises
## 21     50         40         33       34     43
## 22     64         61         52       62     66
## 23     53         66         52       50     63
## 24     40         37         42       58     50
## 25     63         54         42       48     66

B <- as.matrix(attitude[11:15, 1:5])
B

##    rating complaints privileges learning raises
## 11     64         53         53       58     58
## 12     67         60         47       39     59
## 13     69         62         57       42     55
## 14     68         83         83       45     59
## 15     77         77         54       72     79

?solve

## Warning in read.dcf(file.path(p, "DESCRIPTION"), c("Package", "Version")):
## cannot open compressed file '/Library/Frameworks/R.framework/Versions/3.6/
## Resources/library/ggplot2/DESCRIPTION', probable reason 'No such file or
## directory'

## Warning in find.package(if (is.null(package)) loadedNamespaces() else package, :
## there is no package called 'ggplot2'

C <- solve(A) %*% B
C

##                rating complaints privileges  learning     raises
## rating      0.7389616 -0.1158204  0.2187957  1.173421  0.7785334
## complaints -4.6257572 -6.1397730 -8.1338315 -6.403933 -4.3351608
## privileges  6.8562975  7.6917856 12.2993714  7.961175  5.0382583
## learning   -3.3515454 -3.6302589 -5.2339778 -4.925546 -2.9153565
## raises      2.3203939  4.0460887  3.2439410  3.726420  2.9148688

C <- solve(A, B)
C

##                rating complaints privileges  learning     raises
## rating      0.7389616 -0.1158204  0.2187957  1.173421  0.7785334
## complaints -4.6257572 -6.1397730 -8.1338315 -6.403933 -4.3351608
## privileges  6.8562975  7.6917856 12.2993714  7.961175  5.0382583
## learning   -3.3515454 -3.6302589 -5.2339778 -4.925546 -2.9153565
## raises      2.3203939  4.0460887  3.2439410  3.726420  2.9148688

Carregar BrFlights2

dim(BrFlights2)

## Error in eval(expr, envir, enclos): object 'BrFlights2' not found

Em geral tudo que for numérico não pode ser usado como fator.
Não é muito informativo usar estado como fator.
Conta as qtdes das variá?veis.

table(BrFlights2$Pais.Origem)

## Error in table(BrFlights2$Pais.Origem): object 'BrFlights2' not found

BrFlights2$Pais.Origem

## Error in eval(expr, envir, enclos): object 'BrFlights2' not found

Transformou os strings em factors com levels.

factor(BrFlights2$Pais.Origem)

## Error in factor(BrFlights2$Pais.Origem): object 'BrFlights2' not found

?factor

## Warning in read.dcf(file.path(p, "DESCRIPTION"), c("Package", "Version")):
## cannot open compressed file '/Library/Frameworks/R.framework/Versions/3.6/
## Resources/library/ggplot2/DESCRIPTION', probable reason 'No such file or
## directory'

## Warning in find.package(if (is.null(package)) loadedNamespaces() else package, :
## there is no package called 'ggplot2'

dt <- data.frame(Sexo = rep(c("F", "M"), 10))
dt

##    Sexo
## 1     F
## 2     M
## 3     F
## 4     M
## 5     F
## 6     M
## 7     F
## 8     M
## 9     F
## 10    M
## 11    F
## 12    M
## 13    F
## 14    M
## 15    F
## 16    M
## 17    F
## 18    M
## 19    F
## 20    M

dt$Sexo2 <- as.character(dt$Sexo)
dt

##    Sexo Sexo2
## 1     F     F
## 2     M     M
## 3     F     F
## 4     M     M
## 5     F     F
## 6     M     M
## 7     F     F
## 8     M     M
## 9     F     F
## 10    M     M
## 11    F     F
## 12    M     M
## 13    F     F
## 14    M     M
## 15    F     F
## 16    M     M
## 17    F     F
## 18    M     M
## 19    F     F
## 20    M     M

dt$Sexo2 <- factor(dt$Sexo2, c("M", "F"), labels = c("Masculino", "Feminino"))
dt

##    Sexo     Sexo2
## 1     F  Feminino
## 2     M Masculino
## 3     F  Feminino
## 4     M Masculino
## 5     F  Feminino
## 6     M Masculino
## 7     F  Feminino
## 8     M Masculino
## 9     F  Feminino
## 10    M Masculino
## 11    F  Feminino
## 12    M Masculino
## 13    F  Feminino
## 14    M Masculino
## 15    F  Feminino
## 16    M Masculino
## 17    F  Feminino
## 18    M Masculino
## 19    F  Feminino
## 20    M Masculino

dt$Sexo2

##  [1] Feminino  Masculino Feminino  Masculino Feminino  Masculino Feminino 
##  [8] Masculino Feminino  Masculino Feminino  Masculino Feminino  Masculino
## [15] Feminino  Masculino Feminino  Masculino Feminino  Masculino
## Levels: Masculino Feminino

dt$Sexo2 <- factor(dt$Sexo, levels = c("M", "F"), labels = 1:2)
dt

##    Sexo Sexo2
## 1     F     2
## 2     M     1
## 3     F     2
## 4     M     1
## 5     F     2
## 6     M     1
## 7     F     2
## 8     M     1
## 9     F     2
## 10    M     1
## 11    F     2
## 12    M     1
## 13    F     2
## 14    M     1
## 15    F     2
## 16    M     1
## 17    F     2
## 18    M     1
## 19    F     2
## 20    M     1

nrow(BrFlights2)

## Error in nrow(BrFlights2): object 'BrFlights2' not found

atrasos <- BrFlights2$Partida.Prevista - BrFlights2$Partida.Real

## Error in eval(expr, envir, enclos): object 'BrFlights2' not found

atrasos

## Error in eval(expr, envir, enclos): object 'atrasos' not found

Amostras e Simulações
- Há duas familias de numeros aleatorios: uniforme e normal. Gauss analisou que os fenomenos naturais seguem uma dist. normal.
- Na Familia Uniforme a chance (prob) de um elemento ser escolhido é igual a de todos os outros elementos.

# runif --> Random (r) Uniform (unif)
?runif

## Warning in read.dcf(file.path(p, "DESCRIPTION"), c("Package", "Version")):
## cannot open compressed file '/Library/Frameworks/R.framework/Versions/3.6/
## Resources/library/ggplot2/DESCRIPTION', probable reason 'No such file or
## directory'

## Warning in find.package(if (is.null(package)) loadedNamespaces() else package, :
## there is no package called 'ggplot2'

set.seed(1)
amostra <- c("T","R","I","A","N","G","U","L","O")
sample(x = amostra, replace = FALSE)

## [1] "O" "A" "U" "T" "R" "G" "I" "L" "N"

sample(x = amostra, replace = TRUE)

## [1] "R" "I" "T" "N" "N" "G" "U" "O" "N"

sample(x = amostra, size = 5)

## [1] "N" "T" "L" "G" "O"

sample(x = amostra, size = 10, replace = TRUE, prob = c(1,1,5,1,1,1,1,1,5))

##  [1] "A" "O" "O" "G" "O" "I" "A" "N" "U" "I"

#prob nao eh probabilidade e sim peso: p("T") = 1/17 e p("I") = 5/17

set.seed – Util para replicacao de teste. Garante o mesmo resultado apesar da aleatoriedade

rnorm(5)

## [1]  0.59390132  0.91897737  0.78213630  0.07456498 -1.98935170

set.seed(8)
rnorm(5)

## [1] -0.08458607  0.84040013 -0.46348277 -0.55083500  0.73604043

dim(airquality)

## [1] 153   6

summary(airquality)

##      Ozone           Solar.R           Wind             Temp      
##  Min.   :  1.00   Min.   :  7.0   Min.   : 1.700   Min.   :56.00  
##  1st Qu.: 18.00   1st Qu.:115.8   1st Qu.: 7.400   1st Qu.:72.00  
##  Median : 31.50   Median :205.0   Median : 9.700   Median :79.00  
##  Mean   : 42.13   Mean   :185.9   Mean   : 9.958   Mean   :77.88  
##  3rd Qu.: 63.25   3rd Qu.:258.8   3rd Qu.:11.500   3rd Qu.:85.00  
##  Max.   :168.00   Max.   :334.0   Max.   :20.700   Max.   :97.00  
##  NA's   :37       NA's   :7                                       
##      Month            Day      
##  Min.   :5.000   Min.   : 1.0  
##  1st Qu.:6.000   1st Qu.: 8.0  
##  Median :7.000   Median :16.0  
##  Mean   :6.993   Mean   :15.8  
##  3rd Qu.:8.000   3rd Qu.:23.0  
##  Max.   :9.000   Max.   :31.0  
##

head(airquality)

##   Ozone Solar.R Wind Temp Month Day
## 1    41     190  7.4   67     5   1
## 2    36     118  8.0   72     5   2
## 3    12     149 12.6   74     5   3
## 4    18     313 11.5   62     5   4
## 5    NA      NA 14.3   56     5   5
## 6    28      NA 14.9   66     5   6

tail(airquality)

##     Ozone Solar.R Wind Temp Month Day
## 148    14      20 16.6   63     9  25
## 149    30     193  6.9   70     9  26
## 150    NA     145 13.2   77     9  27
## 151    14     191 14.3   75     9  28
## 152    18     131  8.0   76     9  29
## 153    20     223 11.5   68     9  30

sample(c(1:10),10)

##  [1]  1  2  3  8  6  4  7  9 10  5

air <- airquality[sample(1:153,10),]
air

##     Ozone Solar.R Wind Temp Month Day
## 62    135     269  4.1   84     7   1
## 7      23     299  8.6   65     5   7
## 19     30     322 11.5   68     5  19
## 63     49     248  9.2   85     7   2
## 70     97     272  5.7   92     7   9
## 135    21     259 15.5   76     9  12
## 66     64     175  4.6   83     7   5
## 102    NA     222  8.6   92     8  10
## 121   118     225  2.3   94     8  29
## 8      19      99 13.8   59     5   8

set.seed(20)
linhas.idx <- seq_len(nrow(airquality))
linhas.sample <- sample(linhas.idx, 10)
airquality[linhas.sample,]

##     Ozone Solar.R Wind Temp Month Day
## 107    NA      64 11.5   79     8  15
## 120    76     203  9.7   97     8  28
## 130    20     252 10.9   80     9   7
## 98     66      NA  4.6   87     8   6
## 29     45     252 14.9   81     5  29
## 45     NA     332 13.8   80     6  14
## 127    91     189  4.6   93     9   4
## 41     39     323 11.5   87     6  10
## 67     40     314 10.9   83     7   6
## 121   118     225  2.3   94     8  29

as.integer(runif(min = 1, max = 153, n = 10))

##  [1]  17  44 125  75   5  67  12  41  11 138

airquality[as.integer(runif(min = 1, max = 153, n = 10)),]

##     Ozone Solar.R Wind Temp Month Day
## 151    14     191 14.3   75     9  28
## 10     NA     194  8.6   69     5  10
## 103    NA     137 11.5   86     8  11
## 51     13     137 10.3   76     6  20
## 69     97     267  6.3   92     7   8
## 127    91     189  4.6   93     9   4
## 29     45     252 14.9   81     5  29
## 78     35     274 10.3   82     7  17
## 73     10     264 14.3   73     7  12
## 71     85     175  7.4   89     7  10

Poucas vezes usamos o runif ou sample na simulação de dados, a familia uniforme nao é natural (alvo de dardos)

hist(rnorm(100))

hist(rnorm(10000)) # Se eu tiver muito dado simulado, meu modelo chega prox a um resultado teorico.

hist(rnorm(1000, 80, 15))

peso <- rnorm(1000, 80, 15)

summary(peso)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   39.41   69.88   79.17   79.94   90.04  130.52

sd(peso)

## [1] 14.37424

peso <- rnorm(100000, 80, 15)

summary(peso)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   17.07   69.87   79.91   79.98   90.15  140.94

sd(peso) # Chego mais perto do te?rico (=15)

## [1] 14.9562

pnorm
- Faz o acumulado entre 0–x. Se eu quiser o intervalo x-y, tenho que calcular a diferen?a entre p(0–x) - p(0–y).

?pnorm

## Warning in read.dcf(file.path(p, "DESCRIPTION"), c("Package", "Version")):
## cannot open compressed file '/Library/Frameworks/R.framework/Versions/3.6/
## Resources/library/ggplot2/DESCRIPTION', probable reason 'No such file or
## directory'

## Warning in find.package(if (is.null(package)) loadedNamespaces() else package, :
## there is no package called 'ggplot2'

pnorm(70, 80, 15) - pnorm(60, 80, 15)

## [1] 0.1612813

Regressao Linear
- Exercicio

set.seed(45)
b0 <- 0.5
b1 <- 2
x <- rnorm(100, 0, 1)
x

##   [1]  0.34079969 -0.70334030 -0.37953773 -0.74604744 -0.89810733 -0.33479411
##   [7] -0.50137815 -0.17453570  1.80903740 -0.23010497 -1.13041822  0.21598889
##  [13]  1.23223729  1.60935871  0.40155063 -0.27298403 -0.03615234 -0.15031123
##  [19]  3.76881035 -1.65249598 -1.13514510  0.22767017 -0.18331854 -0.41351862
##  [25] -0.43759528 -0.02618435 -0.85983418  0.16654458  1.47549073  0.19542291
##  [31]  0.15942179 -0.72019328 -0.93550254  0.28543230 -0.73923515  0.42914898
##  [37]  2.73398385 -1.33340333  1.86009535  0.24596992 -0.74598942 -1.48413799
##  [43]  0.22204850  0.47782760  0.73119851  0.17210513  1.18669199 -0.35040940
##  [49]  1.14759741  1.35008401  1.11614940  0.20234597  0.11149061 -1.52799033
##  [55]  0.05750731  2.18746007 -0.07095490  1.29299658  0.37687501 -0.81651082
##  [61] -0.07169406 -2.15850547  2.01919496 -0.05012938 -0.28021325  0.31783776
##  [67] -0.96890304 -0.50034234 -0.96092400 -1.59004694  0.37573467  1.02919849
##  [73]  1.22623137  1.04839459  0.16741396  1.13799896  1.05672549 -0.68015871
##  [79] -1.33738964 -1.80310187  0.70097740 -2.04409051 -0.98805538  0.62738221
##  [85] -0.38374189  3.60352286  0.33221058 -1.24505785  0.24736600 -1.40402871
##  [91]  0.90718101 -0.70395328 -1.56977100  0.34531272  0.67993840  1.14271882
##  [97]  0.40591523 -0.91864023  2.29631307 -0.68969735

e <- rnorm(100, 0, 2)
e

##   [1] -3.75659775  2.12868800  2.27665488  1.55921463 -1.26408291  0.37685427
##   [7] -1.81937844 -0.27203422  0.45871256 -1.45026436  1.52226183 -0.15895636
##  [13]  3.45498471  0.81040275 -2.80724337  0.13294523  0.61086046  1.74635528
##  [19] -0.05789542  0.26125767  0.15133924  1.57233132 -3.25560339  0.15629099
##  [25] -1.23012637  0.18654976  0.32920774 -2.14635557 -0.75096643 -0.03949354
##  [31]  1.21682699  0.94841711 -3.38184620  1.84229132  1.04052067  0.87119741
##  [37] -0.47713156 -2.16703385  1.56338695 -1.46717388  0.36607988  0.84414514
##  [43] -0.05537081  0.91068011  2.51271079 -2.66212082 -1.77512795 -0.21009780
##  [49] -0.18099061 -3.60214815  1.42049096  0.08042273  0.59671184  2.48660723
##  [55] -0.70738315 -5.70157860  1.75746243 -4.09245356  3.28924385 -0.83720209
##  [61]  1.83277720  0.72168868  4.40938464  1.73074613  2.99381836  1.34295120
##  [67] -2.41623153 -1.08031926 -1.82448003 -2.12824670 -2.30630212  0.61938098
##  [73]  0.23959470  1.23211873 -1.79065837 -3.52168224 -1.29713661  3.33156120
##  [79]  3.66819053 -3.80747097  3.17767331 -1.02635257  1.68242327 -4.04963704
##  [85]  1.71135381  1.06761329  0.10350465 -0.17619227 -1.78551998 -1.36731370
##  [91]  1.89915756 -1.27262398  2.69238555  1.42654310 -0.56445959 -2.77163920
##  [97] -3.05968686 -0.68812366 -2.60297193  0.05389678

y <- b0 + b1 * x + e 
y

##   [1] -2.574998372  1.222007396  2.017579419  0.567119753 -2.560297571
##   [6]  0.207266055 -2.322134749 -0.121105609  4.576787368 -1.410474305
##  [11] -0.238574610  0.773021417  6.419459284  4.529120168 -1.504142116
##  [16]  0.086977157  1.038555776  1.945732814  7.979725278 -2.543734284
##  [21] -1.618950967  2.527671653 -3.122240463 -0.170746256 -1.605316934
##  [26]  0.634181049 -0.890460614 -1.313266418  2.700015025  0.851352287
##  [31]  2.035670567  0.008030544 -4.752851286  2.913155926  0.062050379
##  [36]  2.229495367  5.490836135 -4.333840506  5.783577638 -0.475234033
##  [41] -0.625898968 -1.624130836  0.888726185  2.366335306  4.475107810
##  [46] -1.817910557  1.098256025 -0.410916597  2.614204214 -0.401980128
##  [51]  4.152789756  0.985114679  1.319693057 -0.069373418 -0.092368523
##  [56] -0.826658460  2.115552638 -1.006460405  4.542993862 -1.970223735
##  [61]  2.189389085 -3.095322249  8.947774567  2.130487362  2.933391864
##  [66]  2.478626715 -3.854037620 -1.581003936 -3.246328026 -4.808340581
##  [71] -1.054832784  3.177777964  3.192057438  3.828907917 -0.955830442
##  [76] -0.745684320  1.316314369  2.471243775  1.493411258 -6.913674722
##  [81]  5.079628119 -4.614533581  0.206312505 -2.294872615  1.443870022
##  [86]  8.774659015  1.267925816 -2.166307968 -0.790787968 -3.675371131
##  [91]  4.213519592 -2.180530534  0.052843550  2.617168551  1.295417206
##  [96]  0.013798435 -1.747856399 -2.025404127  2.489654218 -0.825497906

library(plotly)
plot_ly(x = x, y = y, type = "scatter")

## No scatter mode specifed:
##   Setting the mode to markers
##   Read more about this attribute -> https://plot.ly/r/reference/#scatter-mode

?plot_ly

## Warning in read.dcf(file.path(p, "DESCRIPTION"), c("Package", "Version")):
## cannot open compressed file '/Library/Frameworks/R.framework/Versions/3.6/
## Resources/library/ggplot2/DESCRIPTION', probable reason 'No such file or
## directory'

## Warning in find.package(if (is.null(package)) loadedNamespaces() else package, :
## there is no package called 'ggplot2'

CLASS 04 (19/08/2019)

dim(BrFlights2)

## Error in eval(expr, envir, enclos): object 'BrFlights2' not found

nrow(BrFlights2)

## Error in nrow(BrFlights2): object 'BrFlights2' not found

Exercicio 1

table(BrFlights2$Pais.Origem)

## Error in table(BrFlights2$Pais.Origem): object 'BrFlights2' not found

BrFlights2$Pais.Origem

## Error in eval(expr, envir, enclos): object 'BrFlights2' not found

var2 <- as.factor(BrFlights2$Pais.Origem) -> BrFlights2$Pais.Origem

## Error in is.factor(x): object 'BrFlights2' not found

var3 <- sqrt((BrFlights2$LatOrig - BrFlights2$LatDest)^2 + (BrFlights2$LongOrig - BrFlights2$LongDest)^2) -> BrFlights2$DistEucl

## Error in eval(expr, envir, enclos): object 'BrFlights2' not found

BrFlights2$Atrasos <- BrFlights2$Partida.Real - BrFlights2$Partida.Prevista

## Error in eval(expr, envir, enclos): object 'BrFlights2' not found

max(BrFlights2$Atrasos, na.rm =T)

## Error in eval(expr, envir, enclos): object 'BrFlights2' not found

registro.maior_atraso <- which.max(BrFlights2$Atrasos) # Linha que contem o maior atraso.

## Error in which.max(BrFlights2$Atrasos): object 'BrFlights2' not found

# View(BrFlights2[registro.maior_atraso,])
# View(BrFlights2$Companhia.Aerea[registro.maior_atraso])
# View(BrFlights2[registro.maior_atraso, c(4, 9, 12:15)])

Loop - WHILE

strength = 1000
for (i in 1:12){
  strength = strength * 1.01
}
print(strenght)

## Error in print(strenght): object 'strenght' not found

Exercicio 2

AirPassengers

##      Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
## 1949 112 118 132 129 121 135 148 148 136 119 104 118
## 1950 115 126 141 135 125 149 170 170 158 133 114 140
## 1951 145 150 178 163 172 178 199 199 184 162 146 166
## 1952 171 180 193 181 183 218 230 242 209 191 172 194
## 1953 196 196 236 235 229 243 264 272 237 211 180 201
## 1954 204 188 235 227 234 264 302 293 259 229 203 229
## 1955 242 233 267 269 270 315 364 347 312 274 237 278
## 1956 284 277 317 313 318 374 413 405 355 306 271 306
## 1957 315 301 356 348 355 422 465 467 404 347 305 336
## 1958 340 318 362 348 363 435 491 505 404 359 310 337
## 1959 360 342 406 396 420 472 548 559 463 407 362 405
## 1960 417 391 419 461 472 535 622 606 508 461 390 432

class(AirPassengers)

## [1] "ts"

# Série Temporal: Conjunto de frequecia, cuja cada observacao tem a mesma distancia de tempo,ou seja, cada observacao tem o mesmo periodo.

#View(AirPassengers)

ac <- 0
for ( billy in 1:length(AirPassengers)) {
  if (billy == 1){
    ac[billy] = AirPassengers[billy]
  }else{
  ac[billy] = ac[billy - 1] + AirPassengers[billy]
  }
}
print(ac)

##   [1]   112   230   362   491   612   747   895  1043  1179  1298  1402  1520
##  [13]  1635  1761  1902  2037  2162  2311  2481  2651  2809  2942  3056  3196
##  [25]  3341  3491  3669  3832  4004  4182  4381  4580  4764  4926  5072  5238
##  [37]  5409  5589  5782  5963  6146  6364  6594  6836  7045  7236  7408  7602
##  [49]  7798  7994  8230  8465  8694  8937  9201  9473  9710  9921 10101 10302
##  [61] 10506 10694 10929 11156 11390 11654 11956 12249 12508 12737 12940 13169
##  [73] 13411 13644 13911 14180 14450 14765 15129 15476 15788 16062 16299 16577
##  [85] 16861 17138 17455 17768 18086 18460 18873 19278 19633 19939 20210 20516
##  [97] 20831 21132 21488 21836 22191 22613 23078 23545 23949 24296 24601 24937
## [109] 25277 25595 25957 26305 26668 27103 27594 28099 28503 28862 29172 29509
## [121] 29869 30211 30617 31013 31433 31905 32453 33012 33475 33882 34244 34649
## [133] 35066 35457 35876 36337 36809 37344 37966 38572 39080 39541 39931 40363

Lista todas variaveis carregadas na memoria

ls()

##  [1] "a"             "A"             "ac"            "Age"          
##  [5] "ai"            "air"           "amostra"       "b"            
##  [9] "B"             "b0"            "b1"            "billy"        
## [13] "c"             "C"             "d"             "date_1"       
## [17] "df"            "dia_date"      "dia_texto"     "dia.time1"    
## [21] "dia.time2"     "dt"            "e"             "i"            
## [25] "idades"        "linhas.idx"    "linhas.sample" "lista"        
## [29] "M"             "M0"            "m1"            "M1"           
## [33] "M19"           "m2"            "M2"            "M3"           
## [37] "M4"            "M5"            "M6"            "M7"           
## [41] "M8"            "MT"            "my_seq"        "Name"         
## [45] "peso"          "Sex"           "sexo"          "strength"     
## [49] "vet"           "vet_num"       "vet1"          "vetor_1"      
## [53] "vetor_2"       "vetor_3"       "vetor_4"       "vetor_5"      
## [57] "vetor_6"       "vetor_7"       "vetor_a"       "vetor_b"      
## [61] "vetor_c"       "x"             "y"

Exercicio 3

fatorial <- function(n){
  prod = 1
  while (n >= 1){
    prod = prod * n
    n = n - 1
  }
  return (prod)
}

fatorial(10)

## [1] 3628800

fat2 <- function(n){
  if (n <= 1){
    return(1)
  }else{
    return(n * fatorial(n-1))
  }
}

fat2(10)

## [1] 3628800

# <<- ou ->> Tenta subir ou descer escopos de environments

CLASS 05 (26/8/2019)

Obtendo dados com o R

#setwd() -> Ajusta o diretorio de trabalho
#getwd() -> Obtem o diretorio de trabalho atual
#Caminho Relativo: "./data", "../"
#Caminho absoluto: "/r/fiap/data"
#Formato Windows: "C:\\r\\fiap\\data
#Boa pratica: Separar seus dados de analise dos scripts de analise

Obter dados da Internet

# getwd()
# 
# file.exists ('data')
# 
# if(!file.exists ('data')){
#   dir.create('data')
# }
# 
# file.url = 'https://storage.googleapis.com/ds-publico/IE1-04.xlsx'
# file.local = file.path('./data', basename(file.url))
# download.file(url = file.url, destfile = file.local , mode='wb')
# basename(file.url)
# file.local
# 
# download_url <- function(url1){
#     if(!file.exists ('data')){
#   dir.create('data')
#     }
#   file.url = url1
#   print(paste("URL:", file.url))
#   file.base = basename(file.url)
#   file.dest = file.path('./data', file.base)
#   print(paste("Destino:", file.dest))
#   download.file(url = file.url, destfile = file.dest , mode='wb')
# }
#   
# download_url('https://storage.googleapis.com/ds-publico/Copas.csv' )
# download_url('https://storage.googleapis.com/ds-publico/Copas-Partidas.csv' )
# download_url('https://storage.googleapis.com/ds-publico/Copas-Jogadores.csv' )

read.table abre um arquivo e o converte em data.frame

# library(readr)
# Copas <- read_csv("data/Copas.csv")
# View(Copas)
# 
# library(readr)
# Copas_Partidas <- read_csv("data/Copas-Partidas.csv")
# View(Copas_Partidas)
# 
# library(readr)
# Copas_Jogadores <- read_csv("data/Copas-Jogadores.csv")
# View(Copas_Jogadores)

Limpar as variaveis

#rm(list = ls())

Exercicio

# download_url('https://storage.googleapis.com/ds-publico/cameras.baltimore.xlsx')
# 
# library(readxl)
# cameras_baltimore <- read_excel("data/cameras.baltimore.xlsx")
# View(cameras_baltimore)
# 
# Cam_N_Lat <- which.max(cameras_baltimore$Lat)
# Cam_S_Lat <- which.min(cameras_baltimore$Lat)
# Cam_W_Long <- which.min(cameras_baltimore$Long)
# Cam_E_Long <- which.max(cameras_baltimore$Long)
# 
# View(cameras_baltimore[Cam_N_Lat,])
# View(cameras_baltimore[Cam_S_Lat,])
# View(cameras_baltimore[Cam_E_Long,])
# View(cameras_baltimore[Cam_W_Long,])
# 
# library(dplyr)
# View(starwars)
# View(starwars[which.max(starwars$mass),])
# s2 <- mutate (starwars, imc = mass/ ((height / 100) ^2))
# View(s2)
# View(starwars[which.max(s2$imc),])

Pipe

starwars %>% View(.)

## Error in eval(lhs, parent, parent): object 'starwars' not found

starwars %>% View()

## Error in eval(lhs, parent, parent): object 'starwars' not found

starwars %>% head(. , 6)

## Error in eval(lhs, parent, parent): object 'starwars' not found

7 %>% head(starwars, .)

## Error in head(starwars, .): object 'starwars' not found

starwars %>% filter(species == "Droid")

## Error in eval(lhs, parent, parent): object 'starwars' not found

starwars %>% filter(species == "Droid") %>% View()

## Error in eval(lhs, parent, parent): object 'starwars' not found

load("P:/08IA/BrFlights2.RData")

## Warning in readChar(con, 5L, useBytes = TRUE): cannot open compressed file 'P:/
## 08IA/BrFlights2.RData', probable reason 'No such file or directory'

## Error in readChar(con, 5L, useBytes = TRUE): cannot open the connection

# View(BrFlights2)
# AzulFlights <- BrFlights2 %>% filter(Companhia.Aerea == "AZUL") 
# View(AzulFlights)
# dim(AzulFlights)

Dplyr - Select (Não confunda com select de SQL)

starwars %>% select(name, ends_with("color")) %>% View()

## Error in eval(lhs, parent, parent): object 'starwars' not found

Select pode definir nova ordem de colunas e/ou linhas

AzulFlights <- BrFlights2 %>% filter(Companhia.Aerea == “AZUL”) %>%
select(Companhia.Aerea, Cidade.Origem, Cidade.Destino, Situacao.Voo)

AzulFlights <- BrFlights2 %>% 
              filter(Companhia.Aerea == "AZUL") %>%              
              select(Companhia.Aerea, Cidade.Origem, Cidade.Destino, Situacao.Voo)

## Error in eval(lhs, parent, parent): object 'BrFlights2' not found

# View(AzulFlights)

DPLYR - ARRANGE

starwars %>% arrange(desc(mass))

# View(BrFlights2)

BrFlights2 %>% mutate(TempoAtrasado = Chegada.Real - Chegada.Prevista ) %>%
          filter(Codigo.Tipo.Linha != "Internacional") %>%
          arrange(desc(TempoAtrasado)) %>%
          head(100) %>%
          # View()

## Error: <text>:10:0: unexpected end of input
## 8:           head(100) %>%
## 9:           # View()
##   ^

DYPLR - RENAME

rename(starwars,
       nome = name,
       altura = height,
       massa = mass)

## Error in rename(starwars, nome = name, altura = height, massa = mass): object 'starwars' not found

DYPLR - Agregacoes

starwars %>% 
  group_by(species) %>% 
  summarise(j = n()) %>%
  # View()

starwars %>% 
  group_by(species) %>% 
  summarise(
    j = n(),
    mass = mean(mass, na.rm = TRUE)
    ) %>%
  filter(j > 1) %>%
  # View()

BrFlights2 %>% mutate(TempoAtrasado = Chegada.Real - Chegada.Prevista,
                      DistEucl = sqrt((BrFlights2$LatOrig - BrFlights2$LatDest)^2 + (BrFlights2$LongOrig - BrFlights2$LongDest)^2)) %>%
          arrange(desc(TempoAtrasado)) %>%
          head(100) %>%
          group_by(Companhia.Aerea) %>%
          summarise(
            j = n(),
            atraso = mean(TempoAtrasado, na.rm = TRUE),
            distancia = mean(DistEucl, na.rm = TRUE)
            ) %>%
          # View()

## Error: <text>:26:0: unexpected end of input
## 24:             ) %>%
## 25:           # View()
##    ^

CLASS 06 (16/09/2019)

Plots

x = -10:10
plot(x = x, y = x ** 2, main = 'Parabola')

plot(x = x, y = x ** 2, main = 'Parabola', type = 'l')

plot(x = x, y = x ** 2, main = 'Parabola', type = 'p')

plot(x = x, y = x ** 2, main = 'Parabola', type = 'b')

plot(x = x, y = x ** 2, main = 'Parabola', type = 'o')

plot(x = x, y = x ** 2, main = 'Parabola', type = 'h')

plot(x = x, y = x ** 2, main = 'Parabola', type = 's')

plot(x = x, y = x ** 2, main = 'Parabola', type = 'S')

head(cars)

##   speed dist
## 1     4    2
## 2     4   10
## 3     7    4
## 4     7   22
## 5     8   16
## 6     9   10

summary(cars)

##      speed           dist       
##  Min.   : 4.0   Min.   :  2.00  
##  1st Qu.:12.0   1st Qu.: 26.00  
##  Median :15.0   Median : 36.00  
##  Mean   :15.4   Mean   : 42.98  
##  3rd Qu.:19.0   3rd Qu.: 56.00  
##  Max.   :25.0   Max.   :120.00

plot(x = cars$speed, y = cars$dist)

plot(cars)

*Histograma

?hist

## Warning in read.dcf(file.path(p, "DESCRIPTION"), c("Package", "Version")):
## cannot open compressed file '/Library/Frameworks/R.framework/Versions/3.6/
## Resources/library/ggplot2/DESCRIPTION', probable reason 'No such file or
## directory'

## Warning in find.package(if (is.null(package)) loadedNamespaces() else package, :
## there is no package called 'ggplot2'

hist(x**2)

*BoxPlots

summary(airquality)

##      Ozone           Solar.R           Wind             Temp      
##  Min.   :  1.00   Min.   :  7.0   Min.   : 1.700   Min.   :56.00  
##  1st Qu.: 18.00   1st Qu.:115.8   1st Qu.: 7.400   1st Qu.:72.00  
##  Median : 31.50   Median :205.0   Median : 9.700   Median :79.00  
##  Mean   : 42.13   Mean   :185.9   Mean   : 9.958   Mean   :77.88  
##  3rd Qu.: 63.25   3rd Qu.:258.8   3rd Qu.:11.500   3rd Qu.:85.00  
##  Max.   :168.00   Max.   :334.0   Max.   :20.700   Max.   :97.00  
##  NA's   :37       NA's   :7                                       
##      Month            Day      
##  Min.   :5.000   Min.   : 1.0  
##  1st Qu.:6.000   1st Qu.: 8.0  
##  Median :7.000   Median :16.0  
##  Mean   :6.993   Mean   :15.8  
##  3rd Qu.:8.000   3rd Qu.:23.0  
##  Max.   :9.000   Max.   :31.0  
##

boxplot(airquality)

summary(airquality$Ozone)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    1.00   18.00   31.50   42.13   63.25  168.00      37

boxplot(airquality$Ozone, outline =  T)

boxplot(airquality$Ozone, outline =  F)

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

airquality

##     Ozone Solar.R Wind Temp Month Day
## 1      41     190  7.4   67     5   1
## 2      36     118  8.0   72     5   2
## 3      12     149 12.6   74     5   3
## 4      18     313 11.5   62     5   4
## 5      NA      NA 14.3   56     5   5
## 6      28      NA 14.9   66     5   6
## 7      23     299  8.6   65     5   7
## 8      19      99 13.8   59     5   8
## 9       8      19 20.1   61     5   9
## 10     NA     194  8.6   69     5  10
## 11      7      NA  6.9   74     5  11
## 12     16     256  9.7   69     5  12
## 13     11     290  9.2   66     5  13
## 14     14     274 10.9   68     5  14
## 15     18      65 13.2   58     5  15
## 16     14     334 11.5   64     5  16
## 17     34     307 12.0   66     5  17
## 18      6      78 18.4   57     5  18
## 19     30     322 11.5   68     5  19
## 20     11      44  9.7   62     5  20
## 21      1       8  9.7   59     5  21
## 22     11     320 16.6   73     5  22
## 23      4      25  9.7   61     5  23
## 24     32      92 12.0   61     5  24
## 25     NA      66 16.6   57     5  25
## 26     NA     266 14.9   58     5  26
## 27     NA      NA  8.0   57     5  27
## 28     23      13 12.0   67     5  28
## 29     45     252 14.9   81     5  29
## 30    115     223  5.7   79     5  30
## 31     37     279  7.4   76     5  31
## 32     NA     286  8.6   78     6   1
## 33     NA     287  9.7   74     6   2
## 34     NA     242 16.1   67     6   3
## 35     NA     186  9.2   84     6   4
## 36     NA     220  8.6   85     6   5
## 37     NA     264 14.3   79     6   6
## 38     29     127  9.7   82     6   7
## 39     NA     273  6.9   87     6   8
## 40     71     291 13.8   90     6   9
## 41     39     323 11.5   87     6  10
## 42     NA     259 10.9   93     6  11
## 43     NA     250  9.2   92     6  12
## 44     23     148  8.0   82     6  13
## 45     NA     332 13.8   80     6  14
## 46     NA     322 11.5   79     6  15
## 47     21     191 14.9   77     6  16
## 48     37     284 20.7   72     6  17
## 49     20      37  9.2   65     6  18
## 50     12     120 11.5   73     6  19
## 51     13     137 10.3   76     6  20
## 52     NA     150  6.3   77     6  21
## 53     NA      59  1.7   76     6  22
## 54     NA      91  4.6   76     6  23
## 55     NA     250  6.3   76     6  24
## 56     NA     135  8.0   75     6  25
## 57     NA     127  8.0   78     6  26
## 58     NA      47 10.3   73     6  27
## 59     NA      98 11.5   80     6  28
## 60     NA      31 14.9   77     6  29
## 61     NA     138  8.0   83     6  30
## 62    135     269  4.1   84     7   1
## 63     49     248  9.2   85     7   2
## 64     32     236  9.2   81     7   3
## 65     NA     101 10.9   84     7   4
## 66     64     175  4.6   83     7   5
## 67     40     314 10.9   83     7   6
## 68     77     276  5.1   88     7   7
## 69     97     267  6.3   92     7   8
## 70     97     272  5.7   92     7   9
## 71     85     175  7.4   89     7  10
## 72     NA     139  8.6   82     7  11
## 73     10     264 14.3   73     7  12
## 74     27     175 14.9   81     7  13
## 75     NA     291 14.9   91     7  14
## 76      7      48 14.3   80     7  15
## 77     48     260  6.9   81     7  16
## 78     35     274 10.3   82     7  17
## 79     61     285  6.3   84     7  18
## 80     79     187  5.1   87     7  19
## 81     63     220 11.5   85     7  20
## 82     16       7  6.9   74     7  21
## 83     NA     258  9.7   81     7  22
## 84     NA     295 11.5   82     7  23
## 85     80     294  8.6   86     7  24
## 86    108     223  8.0   85     7  25
## 87     20      81  8.6   82     7  26
## 88     52      82 12.0   86     7  27
## 89     82     213  7.4   88     7  28
## 90     50     275  7.4   86     7  29
## 91     64     253  7.4   83     7  30
## 92     59     254  9.2   81     7  31
## 93     39      83  6.9   81     8   1
## 94      9      24 13.8   81     8   2
## 95     16      77  7.4   82     8   3
## 96     78      NA  6.9   86     8   4
## 97     35      NA  7.4   85     8   5
## 98     66      NA  4.6   87     8   6
## 99    122     255  4.0   89     8   7
## 100    89     229 10.3   90     8   8
## 101   110     207  8.0   90     8   9
## 102    NA     222  8.6   92     8  10
## 103    NA     137 11.5   86     8  11
## 104    44     192 11.5   86     8  12
## 105    28     273 11.5   82     8  13
## 106    65     157  9.7   80     8  14
## 107    NA      64 11.5   79     8  15
## 108    22      71 10.3   77     8  16
## 109    59      51  6.3   79     8  17
## 110    23     115  7.4   76     8  18
## 111    31     244 10.9   78     8  19
## 112    44     190 10.3   78     8  20
## 113    21     259 15.5   77     8  21
## 114     9      36 14.3   72     8  22
## 115    NA     255 12.6   75     8  23
## 116    45     212  9.7   79     8  24
## 117   168     238  3.4   81     8  25
## 118    73     215  8.0   86     8  26
## 119    NA     153  5.7   88     8  27
## 120    76     203  9.7   97     8  28
## 121   118     225  2.3   94     8  29
## 122    84     237  6.3   96     8  30
## 123    85     188  6.3   94     8  31
## 124    96     167  6.9   91     9   1
## 125    78     197  5.1   92     9   2
## 126    73     183  2.8   93     9   3
## 127    91     189  4.6   93     9   4
## 128    47      95  7.4   87     9   5
## 129    32      92 15.5   84     9   6
## 130    20     252 10.9   80     9   7
## 131    23     220 10.3   78     9   8
## 132    21     230 10.9   75     9   9
## 133    24     259  9.7   73     9  10
## 134    44     236 14.9   81     9  11
## 135    21     259 15.5   76     9  12
## 136    28     238  6.3   77     9  13
## 137     9      24 10.9   71     9  14
## 138    13     112 11.5   71     9  15
## 139    46     237  6.9   78     9  16
## 140    18     224 13.8   67     9  17
## 141    13      27 10.3   76     9  18
## 142    24     238 10.3   68     9  19
## 143    16     201  8.0   82     9  20
## 144    13     238 12.6   64     9  21
## 145    23      14  9.2   71     9  22
## 146    36     139 10.3   81     9  23
## 147     7      49 10.3   69     9  24
## 148    14      20 16.6   63     9  25
## 149    30     193  6.9   70     9  26
## 150    NA     145 13.2   77     9  27
## 151    14     191 14.3   75     9  28
## 152    18     131  8.0   76     9  29
## 153    20     223 11.5   68     9  30

# View(airquality)

Exemplo 1a

airquality %>% 
  select(Ozone, Month) %>%
  filter(Month == '5') %>%
  arrange(Ozone) -> gm
summary(gm$Ozone)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    1.00   11.00   18.00   23.62   31.50  115.00       5

plot(seq_along(gm$Ozone), gm$Ozone)
lines(x = c(1,31), y = c(1,1), col = "blue")
lines(x = c(1,31), y = c(11,11), col = "blue")
lines(x = c(1,31), y = c(18,18), col = "red")
lines(x = c(1,31), y = c(31.5,31.5), col = "blue")
lines(x = c(1,31), y = c(115,115), col = "blue")

*Exemplo 1b

airquality %>% 
  filter(Month == '5') %>%
  select(Ozone) %>%
  arrange(Ozone) %>% 
  unlist()-> gm
summary(gm)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    1.00   11.00   18.00   23.62   31.50  115.00       5

plot(seq_along(gm), gm)
lines(x = c(1,31), y = c(1,1), col = "blue")
lines(x = c(1,31), y = c(11,11), col = "blue")
lines(x = c(1,31), y = c(18,18), col = "red")
lines(x = c(1,31), y = c(31.5,31.5), col = "blue")
lines(x = c(1,31), y = c(115,115), col = "blue")

Boxplot using Formula

a<- formula(Ozone ~ Wind) #Responda Ozone em funcao de Wind
class(a)

## [1] "formula"

boxplot(formula(airquality$Ozone ~ airquality$Month))

f1 <- formula(Ozone ~ Month)
boxplot(f1, data = airquality)

env_meu <- new.env()

env_meu$Ozo <- airquality$Ozone
env_meu$Mon <- airquality$Month

boxplot(formula = Ozo ~ Mon)

## Error in eval(predvars, data, env): object 'Ozo' not found

boxplot(formula = Ozo ~ Mon, data = env_meu)

Ozo <- airquality$Ozone
Mon <- airquality$Month
boxplot(formula = Ozo ~ Mon)

Temp <- airquality$Temp
boxplot(formula = Temp ~ Mon)

Wind <- airquality$Wind
boxplot(formula = Wind ~ Mon)

Solar <- airquality$Solar.R
boxplot(formula = Solar ~ Mon)

Relacao entre variaveis

plot(formula = Ozo ~ Wind)
my_reg <- lm(data = airquality, formula = Ozo ~ Wind)
my_reg

## 
## Call:
## lm(formula = Ozo ~ Wind, data = airquality)
## 
## Coefficients:
## (Intercept)         Wind  
##      96.873       -5.551

abline(my_reg, col = "red")

Multiplos Graficos

par(mfrow=c(1,2))
plot(airquality$Wind, airquality$Ozone)
plot(airquality$Solar.R, airquality$Ozone)

par(mfrow=c(1,1))

Plotly

library(plotly)

Monta o gráfico e armazena em p

plot_ly(data = airquality,
        x = ~Wind, y = ~Ozone,
        text = ~paste0(Day, '/', Month),
        type = 'scatter', mode ='markers') -> p

Exibe p

print( p )

## Warning: Ignoring 37 observations

Lattice

library(lattice)
state <- data.frame(state.x77,
                    region = state.region)

xyplot(Life.Exp ~ Income | region,
       data = state,
       layout = c(4, 1))

Shiny App

shiny::shinyAppDir("teste")

Shiny applications not supported in static R Markdown documents

Distribution Types

shiny::shinyAppDir("dist")

## Error in shiny::shinyAppDir("dist"): No Shiny application exists at the path "dist"

#https://stackoverflow.com/questions/44256853/rendering-images-in-documents-and-embedded-shiny-apps

Case Study

Proposal: I intend to show in the next lines the resolution of a problem presented in the book: Bussab,W.O. ; Morettin, P.A. Estatística Básica. São Paulo: 2017 Saraiva Educação.

Inference for various populations

A psychologist is investigating the relationship between the time it takes for an individual to react to a visual stimulus $(y)$ and some factors such as gender $(w)$, age $(x)$, and visual acuity ($z$, measured as a percentage). The results were tabled, as follows:

n <- c(1:20)
y <- c(96,92,106,100,98,104,110,101,116,106,109,100,112,105,118,108,113,112,127,117)
x <- c(rep(20,4),rep(25,4),rep(30,4),rep(35,4),rep(40,4))
w <- c('h','m','h','m','m','h','h','m','m','h','h','m','m','m','h','h','m','m','h','h')
z <- c(90,100,80,90,100,90,80,90,70,90,90,80,90,80,70,90,90,90,60,80)  

my_data <- data.frame(n,y,w,x,z)  

knitr::kable(my_data, caption = "Reaction time to a visual stimulus (y) and visual acuity (z) of 20 individuals, by sex (w) and age (x)", align = c('c', 'c', 'c'))

Reaction time to a visual stimulus (y) and visual acuity (z) of 20 individuals, by sex (w) and age (x)
n	y	w	x	z
1	96	h	20	90
2	92	m	20	100
3	106	h	20	80
4	100	m	20	90
5	98	m	25	100
6	104	h	25	90
7	110	h	25	80
8	101	m	25	90
9	116	m	30	70
10	106	h	30	90
11	109	h	30	90
12	100	m	30	80
13	112	m	35	90
14	105	m	35	80
15	118	h	35	70
16	108	h	35	90
17	113	m	40	90
18	112	m	40	90
19	127	h	40	60
20	117	h	40	80

paste("We have the reaction time for n =",length(y), "individuals. (values for random variable y).")

## [1] "We have the reaction time for n = 20 individuals. (values for random variable y)."

We observe we have two levels for the sex factor:
- $i = 1$: male (H)
- $i = 2$: female (M)

paste("n1 = n2 =", length(w) / 2)

## [1] "n1 = n2 = 10"

The age factor has 5 levels:
- $i = 1$: individuals with 20 years old,
- $i = 2$: individuals with 25 years old,
- $i = 3$: individuals with 30 years old,
- $i = 4$: individuals with 35 years old,
- $i = 5$: individuals with 40 years old,

paste("n1 = n2 = n3 = n4 = n5 =", length(x) / 5)

## [1] "n1 = n2 = n3 = n4 = n5 = 4"

Visual acuity as a percentage of complete vision also generates five levels:
- $i = 1$: individuals with 100% of acuity,
- $i = 2$: individuals with 90% of acuity,
- $i = 3$: individuals with 80% of acuity,
- $i = 4$: individuals with 70% of acuity,
- $i = 5$: individuals with 60% of acuity,
- $n_1 = 2, n_2 = 10, n_3 = 5, n_4 = 2, n_5 = 1$.

Therefore, it was not possible to control the variable $z$ a priori as the other two, since it requires ophthalmic examinations for its measurement. Hence, the unbalance of the observed sizes. This factor is known as cofactor type.

Thus, for the sex factor, we have $i = 1, 2, j = 1, 2, 3, ..., 10$, and for the age factor, the same model with $i = 1, 2, ..., 5, j = 1, 2, 3, 4$.

Figure 1 shows the graphic model of this experiment:

plot(formula = y ~ x, main = "plot(formula = y ~x)")

Simple Linear Regression Model

A simple linear regression model can be represented as: $y_i = α + βx_i + e_i,i = 1,2,...,n$

The amount of information lost by the model or the sum of squares of errors (or deviations) is given by: \[SQ(α,β)= ∑ (e_i )^2 = ∑ (y_i-(α+ β∙x_i ))^2\]

To find the minimum value of SQ, we must derive SQ with respect to $α$ and $β$ and match the derivatives to zero, obtaining:

\[SQ_β= 2∙∑(y_i-α-β∙x_i )∙(-x_i ) = 0\] \[SQ_α= 2∙∑(y_i-α-β∙x_i )∙(-1) = 0\]

Solving this system of equations we get:

\[α ̂= (∑ y_i)/n- β ̂ (∑x_i )/n= y ̅- β ̂∙x ̅\] \[β ̂= (∑x_i y_i-((∑x_i )∙(∑y_i ))/n)/(∑x_i^2-(∑x_i )^2/n)= (∑x_i y_i-n(xy) ̅ /(∑x_i^2-nx ̅^2 )\]

Where, $α ̂$ and $β ̂$ are the estimated linear and angular coefficients, respectively.

In our Case Study, we assume:

$y_i$: reaction time of i-th individual;
$x_i$: age of i-th individual;
$e_i$: deviation, $i = 1, 2, …, 20.

$n = 20$,
$∑y_i= 2150$,
$∑i=600$,
$∑x_i∙y_i=65400$,
$y ̅=107.5$,
$x ̅=30$,
$∑x^2=1900$

\[(β ) ̂=(65400- (20)(30)(107.5))/(19000-(20) (30)^2 )=0,90\] \[α ̂=107.5-(0,90)(30)=80,5\] What gives us the adjusted model: \[y ̂=80,5+0,9∙x_i,i=1,2,…,20\]

With this model, we can predict, for example, the average reaction time for 33-year-olds, which is an unobserved age group: \[y ̂(33)=80,5+0,9(33)=110,2.\]

The graph illustrated bellow adds to the previous one the line obtained by the calculated linear regression.

plot(formula = y ~ x, main = "lm(data = my_data, formula = y ~ x)")
abline(lm(data = my_data, formula = y ~ x), col = "red")